Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare a non-readonly, non-destructive, closed-world mutation, and the description adds genuinely new behavioral facts: mandatory checks, price calculation, cost reservation, queue insertion, and that dryRun leaves balance and queue untouched (the schema's dryRun has no description at all). It still omits auth/permission requirements and failure behavior (e.g. what happens when the max-cost abort fires).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and side effects, and each sentence carries distinct information (pipeline, card behavior, confirmation guidance, dryRun). The German/English duplication roughly doubles the length without adding content, which costs it a point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 29-parameter submission tool with no output schema, the description covers the workflow and side effects well but says nothing about what is returned (approval id, queue position, quoted cost). With no output schema present, return-value semantics are documented nowhere, leaving a real completeness gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 28% across 29 parameters, so the description is expected to compensate, and it does clarify dryRun semantics, the cost-abort limit associated with maxCostEuros, and recipient/AVV checks. However, most parameters (express, scheduledAt, signatureId, templateId, includeSignature, approvalMode, auditTag, reasoning, color) receive no semantic help anywhere.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('submits a letter for human approval') and enumerates the full pipeline (validates details, builds PDF, prices, reserves cost, queues approval), which clearly separates it from draft-creation siblings like letter_create_draft. It never names or contrasts an alternative sibling (e.g. order_send, approval_decide), so the differentiation is inferential rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Describes the flow after submission (card appears, short confirmation suffices, self_approve shows Approve/Reject, otherwise portal) but gives no explicit when-to-use vs letter_create_draft, order_send or approval_decide, and no stated prerequisites. Usage is implied by the workflow narrative rather than stated as selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.